Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add allsmog/vuln-scout --skill mixed-language-monoreposgit clone --depth 1 https://github.com/allsmog/vuln-scoutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/allsmog/vuln-scout/mixed-language-monorepos)<a href="https://agentmods.dev/skills/allsmog/vuln-scout/mixed-language-monorepos"><img src="https://agentmods.dev/badge/skills/allsmog/vuln-scout/mixed-language-monorepos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/allsmog/vuln-scout/mixed-language-monorepos"><img src="https://agentmods.dev/badge/skills/allsmog/vuln-scout/mixed-language-monorepos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.04936 |
| Opus 5 | $0.00036 | $0.02468 |
| Sonnet 5 | $0.00014 | $0.00987 |
| Haiku 4.5 | $0.00007 | $0.00494 |
Grade A, and why
Mixed-Language Monorepos scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- TypeScript: Use JS/TS sinks (eval, child_process, DOM manipulation) How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mixed-Language Monorepo Security Analysis
Purpose
Provide comprehensive guidance for security analysis of polyglot codebases where multiple services are written in different programming languages. These are increasingly common in modern architectures (Go APIs + Python ML + TypeScript frontends).
When to Use
Activate this skill when:
- Monorepo contains services in 2+ different languages
- Microservices architecture with polyglot stack
- User mentions "Go + Python", "TypeScript + Java", etc.
- Cross-service API security analysis needed
- gRPC/protobuf, OpenAPI, or GraphQL schemas present
Core Challenges
Why Mixed-Language is Different
| Single-Language | Mixed-Language |
|---|---|
| One compression strategy | Per-service strategy needed |
| Unified sink database | Multiple sink databases |
| Same vulnerability patterns | Language-specific + cross-service patterns |
| Simple trust boundaries | Complex inter-service boundaries |
| One toolchain | Multiple toolchains (Semgrep rules vary) |
Common Polyglot Patterns
| Pattern | Example | Security Concern |
|---|---|---|
| API Gateway + Services | Go gateway → Python/Java services | Gateway bypass, auth propagation |
| BFF + Backend | TS frontend → Go API → Python ML | Input validation gaps |
| Event-Driven | Services communicate via Kafka/RabbitMQ | Message injection, schema drift |
| Sidecar/Service Mesh | Envoy/Istio + any language | mTLS config, RBAC policies |
Detection
Step 1: Identify All Languages
# Count files by language
echo "=== Language Distribution ==="
echo "Go: $(find . -name '*.go' ! -path '*/vendor/*' ! -name '*_test.go' 2>/dev/null | wc -l)"
echo "Python: $(find . -name '*.py' ! -path '*/.venv/*' ! -path '*/venv/*' ! -name 'test_*.py' 2>/dev/null | wc -l)"
echo "TypeScript: $(find . \( -name '*.ts' -o -name '*.tsx' \) ! -path '*/node_modules/*' ! -name '*.test.*' ! -name '*.spec.*' 2>/dev/null | wc -l)"
echo "JavaScript: $(find . \( -name '*.js' -o -name '*.jsx' \) ! -path '*/node_modules/*' ! -name '*.test.*' ! -name '*.spec.*' 2>/dev/null | wc -l)"
echo "Java: $(find . -name '*.java' ! -path '*/test/*' ! -name '*Test.java' 2>/dev/null | wc -l)"
echo "Rust: $(find . -name '*.rs' ! -path '*/target/*' ! -name '*_test.rs' 2>/dev/null | wc -l)"
echo "PHP: $(find . -name '*.php' ! -path '*/vendor/*' ! -name '*Test.php' 2>/dev/null | wc -l)"
echo "C#: $(find . -name '*.cs' ! -path '*/bin/*' ! -path '*/obj/*' ! -name '*Test*.cs' 2>/dev/null | wc -l)"
echo "Ruby: $(find . -name '*.rb' ! -path '*/vendor/*' ! -name '*_spec.rb' ! -name '*_test.rb' 2>/dev/null | wc -l)"
echo "Solidity: $(find . -name '*.sol' ! -path '*/node_modules/*' ! -name '*Test.sol' 2>/dev/null | wc -l)"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 494 lines · 71 tokens per session scan A 20a3e53c9aba
Mixed-Language Monorepos is a skill published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 4,936 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sast-semgrep
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…
sast-semgrep
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…
secure-code-review
Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization, cryptography, or input handling is shared. Produces findings mapped to ASVS controls and CWE identifiers with severity…
sast-config
Reviews and tunes SAST tool configurations against OWASP ASVS 4.0.3 and CWE Top 25. Auto-invoked when reviewing Semgrep rules, CodeQL queries, SAST CI integration, or false positive triage workflows. Produces a SAST maturity assessment covering rule authoring, severity tuning, custom rule development, and CI…
crypto-source-audit
Audits cryptographic source code for timing side channels, missing secret zeroization, non-constant-time comparison, and weak randomness. Use when reviewing crypto primitives, key/nonce/PSK handling, TLS or handshake code, signature or KEM implementations, or any function that touches secret key material, including…
security-code-review
Full security code review with Semgrep Pro scan, taint analysis, CWE mapping, OWASP Top 10 coverage, and generation of a formal Security Code Review Report saved to /security-review/ in the repository root. Use when reviewing code for vulnerabilities, auditing a file for security issues, or before merging…